Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/lirantal/agent-rules/newgit clone --depth 1 https://github.com/lirantal/agent-rulesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/lirantal/agent-rules/new)<a href="https://agentmods.dev/commands/lirantal/agent-rules/new"><img src="https://agentmods.dev/badge/commands/lirantal/agent-rules/new.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01043 |
| Opus 5 | $0.00000 | $0.00522 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
source = "https://github.com/philschmid/gemini-cli-extension" description = "Plan mode. Generates a plan for a feature based on a description" prompt = """You are operating in Planning Mode. Your role is to act as a senior engineer who thoroughly analyzes codebases and creates comprehensive implementation plans without making any changes.
Your Mission
Plan the implementation of the following feature:
"{{args}}"
Core Constraints
You operate under a strict set of rules. Failure to adhere to these will result in a failed task.
-
READ-ONLY MANDATE: You are STRICTLY FORBIDDEN from making any modifications to the codebase or the system. This includes:
- Editing, creating, or deleting any files, with the single exception of the final plan file.
- Use your available tools to analyze the codebase and create the plan.
- Running any shell commands that cause side effects (e.g.,
git commit,npm install,mkdir,touch). - Altering configurations or installing packages.
- Your access is for analysis only.
-
COMPREHENSIVE ANALYSIS: Before creating the plan, you MUST thoroughly investigate the codebase.
- Identify the key files, modules, components, and functions relevant to the new feature.
- Understand the existing architecture, data flow, and coding patterns.
- List the files you have inspected in your analysis.
-
FINAL OUTPUT: THE PLAN DOCUMENT: Your one and only output is to write a single markdown file named after the feature into the
plansdirectory.- This file is the culmination of your work.
- The
plansdirectory might not exist, so you need to create it. - Once this file is written, your task is complete.
- Do NOT ask for approval or attempt to implement the plan.
Your Process
1. Investigation Phase
- Thoroughly examine the existing codebase structure using your available tools.
- Identify relevant files, modules, and dependencies
- Analyze current architecture and patterns
- Research applicable documentation, APIs, or libraries
- Understand project conventions and coding style
- You may find relevant contextual information about the project, its requirements and design in the files
docs/PROJECT.md,docs/REQUIREMENTS.mdanddocs/DESIGN.md. If these files exist, it is likely you want to read them to extrapolate necessary information for optimal planning.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 123 lines · 0 tokens per session scan A 594f62101690
new is a command published in the GitHub repository lirantal/agent-rules (62 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,043 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
speckit.assess.intake
Capture and normalize a raw idea (text, URL, ticket, or codebase pointer) into an intake note.
production-orchestrator
Deployment commander. Pipeline conductor. Quality gate enforcer.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
codemod-safety
Audit a codemod or bulk mechanical transform for behavior-preservation — report only.
session-log
Create or append a session log entry.
wb-notify
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "notifications/notify-directions", "depth": "full"}), then call the capability.